Related papers: Two-Faced Social Agents: Context Collapse in Role-…

With large language models (LLMs) like GPT-4 appearing to behave increasingly human-like in text-based interactions, it has become popular to attempt to evaluate personality traits of LLMs using questionnaires originally developed for…

Multimodal large language models (MLLMs) have enabled GUI agents to interact with operating systems by grounding language into spatial actions. Despite their promising performance, these models frequently exhibit hallucinations-systematic…

We characterize a compositional architecture of literary primitives in two instruction-tuned large language models (Llama 3.1 8B-Instruct and Gemma 2 9B-IT) via sparse autoencoders on mid-depth residual streams. Four feature classes emerge:…

The deployment of large language models (LLMs) raises concerns regarding their cultural misalignment and potential ramifications on individuals and societies with diverse cultural backgrounds. While the discourse has focused mainly on…

Large language models (LLMs) are increasingly applied in educational, clinical, and professional settings, but their tendency for sycophancy -- prioritizing user agreement over independent reasoning -- poses risks to reliability. This study…

Automated sentiment analysis using Large Language Model (LLM)-based models like ChatGPT, Gemini or LLaMA2 is becoming widespread, both in academic research and in industrial applications. However, assessment and validation of their…

We propose a novel way to evaluate sycophancy of LLMs in a direct and neutral way, mitigating various forms of uncontrolled bias, noise, or manipulative language, deliberately injected to prompts in prior works. A key novelty in our…

Mental health disorders impose a substantial global socioeconomic burden. While large language models (LLMs) offer 24/7, non-judgmental interactions to address this gap, pretrained models lack contextual coherence and emotional alignment…

Telling an LLM to "be enthusiastic" raises its sycophancy rate from 30\% to 50\% on a lightly-aligned model, but has zero effect on a strongly-aligned one. We define this gap as the alignment floor,…

Multi-turn conversational attacks, which leverage psychological principles like Foot-in-the-Door (FITD), where a small initial request paves the way for a more significant one, to bypass safety alignments, pose a persistent threat to Large…

The increased use of Large Language Models (LLMs) in sensitive domains leads to growing interest in how their confidence scores correspond to fairness and bias. This study examines the alignment between LLM-predicted confidence and…

Large Language Models (LLMs) like GPT-4 and Gemini have significantly advanced artificial intelligence by enabling machines to generate and comprehend human-like text. Despite their impressive capabilities, LLMs are not immune to…

While both agent interaction and personalisation are vibrant topics in research on large language models (LLMs), there has been limited focus on the effect of language interaction on the behaviour of persona-conditioned LLM agents. Such an…

Homogeneity bias in Large Language Models (LLMs) refers to their tendency to homogenize the representations of some groups compared to others. Previous studies documenting this bias have predominantly used encoder models, which may have…

The ability of large language models (LLMs) to recall and retrieve information from long contexts is critical for many real-world applications. Prior work (Liu et al., 2023) reported that LLMs suffer significant drops in retrieval accuracy…

When instructed to underperform on multiple-choice evaluations, do language models engage with question content or fall back on positional shortcuts? We map the boundary between these regimes using a six-condition adversarial…

Recent advancements in Large Language Models(LLMs) have been notable, yet widespread enterprise adoption remains limited due to various constraints. This paper examines bias in LLMs-a crucial issue affecting their usability, reliability,…

Large Language Models (LLMs) are increasingly involved in high-stakes domains, yet how they reason about socially sensitive decisions remains underexplored. We present a large-scale audit of LLMs' treatment of socioeconomic status (SES) in…

The recent boom and rapid integration of Large Language Models (LLMs) into a wide range of applications warrants a deeper understanding of their security and safety vulnerabilities. This paper presents a comparative analysis of the…

This position paper argues that effective tutoring requires corrective friction: surfacing misconceptions and challenging them supportively to drive conceptual change. Yet preference-aligned LLMs can trade epistemic rigor for agreeableness.…